AI Paper Atlas

Research map / Benchmarks / MOT16

MOT16 leaderboard

27 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on MOT16. Best MOTA: 76.6 (CorrTracker, CVPR 2021).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

MOT16 · MOTA

24 papers, each with its best reported number for its own method; higher is better.

#MOTA ↑MethodPaperTopic
176.6CorrTracker
FairMOT
Multiple Object Tracking With Correlation Learning
CVPR 2021 · Table: Comparisons on MOT benc
Tracking
276.5ours (MNT+RTU)A General Recurrent Tracking Framework Without Real Data
ICCV 2021 · Table 5
Tracking
376.4OMC
CSTrack
One More Check: Making “Fake Background” Be Tracked Again
AAAI 2022 · Table: Comparison with the sta
Tracking
474.7UniTrack ImageNet
ResNet-18
Do Different Tracking Tasks Require Different Appearance Models?
NeurIPS 2021 · Table: Comparison with task-sp
Self-supervised and contrastive
574.2UTT-FairMOT
ResNet
Unified Transformer Tracker for Object Tracking
CVPR 2022 · Table 2
Tracking
672.6MeMOTMeMOT: Multi-Object Tracking With Memory
CVPR 2022 · Table 1
Tracking
772.1SOTMOT
CenterNet
Improving Multiple Object Tracking With Single Object Tracking
CVPR 2021 · Table 2
Tracking
871FairMOT(+Ours)
FairMOT
Delving into the Trajectory Long-tail Distribution for Muti-object Tracking
CVPR 2024 · Table 2
Tracking
970.1TraDeS
CenterNet
Track To Detect and Segment: An Online Multi-Object Tracker
CVPR 2021 · MOT16 Test Set table
Tracking
1069.8QDTrack
Faster R-CNN
Quasi-Dense Similarity Learning for Multiple Object Tracking
CVPR 2021 · Table 1
Tracking
14 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

MOT16 · IDF1

21 papers, each with its best reported number for its own method; higher is better.

#IDF1 ↑MethodPaperTopic
176ours (MNT+RTU)A General Recurrent Tracking Framework Without Real Data
ICCV 2021 · Table 5
Tracking
274.3CorrTracker
FairMOT
Multiple Object Tracking With Correlation Learning
CVPR 2021 · Table: Comparisons on MOT benc
Tracking
374.1OMC
CSTrack
One More Check: Making “Fake Background” Be Tracked Again
AAAI 2022 · Table: Comparison with the sta
Tracking
472.3SOTMOT
CenterNet
Improving Multiple Object Tracking With Single Object Tracking
CVPR 2021 · Table 2
Tracking
571.8UniTrack ImageNet
ResNet-18
Do Different Tracking Tasks Require Different Appearance Models?
NeurIPS 2021 · Table: Comparison with task-sp
Self-supervised and contrastive
671.3FairMOT(+Ours)
FairMOT
Delving into the Trajectory Long-tail Distribution for Muti-object Tracking
CVPR 2024 · Table 2
Tracking
770.6GMTCT_simInt
CenterTrack detections
Learnable Graph Matching: Incorporating Graph Partitioning With Deep Feature Learning for Multiple Object Tracking
CVPR 2021 · Table: Comparison with State-o
Graph algorithms and clustering
869.7MeMOTMeMOT: Multi-Object Tracking With Memory
CVPR 2022 · Table 1
Tracking
968.3SQE self-optimizationSQE: a Self Quality Evaluation Metric for Parameters Optimization in Multi-Object Tracking
CVPR 2020 · Practical testing table
Tracking
1067.6LPC_MOT (Ours)Learning a Proposal Classifier for Multiple Object Tracking
CVPR 2021 · Table MOT16
Tracking
11 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.